No abstract

Introduction:  The term spitzoid melanoma (SM) is reserved for a rare group of tumors with striking resemblance to Spitz nevus, often developing in children diagnosed in retrospect after the development of metastases. Objectives:  To determine the biological significance of SM and to analyze the effectiveness of adjuvant diagnostic techniques. Materials and methods:  A retrospective, observational study of 38 cases of SM in patients younger than 18 years. Histological type, Clark level and Breslow thickness, radial and vertical growth phase, mitotic count/mm2, ulceration, regression, vascular and perineural invasion, satellitosis, cytology and associated nevi were reviewed. An immunohistochemical analysis with HMB45 and Ki67 was performed in 10 cases. These features were correlated to patient’s stage and outcome. Results:  Analysis of histological and immunohistochemical features should allow accurate diagnosis in most cases. Given the low mortality rate, no conclusions about the prognostic significance of histological parameters of the primary tumor could be established. Conclusion:  We report the largest series of SM from a unique center. Although these patients may have a better prognosis than adults, some patients with SM develop metastasis and die, particularly after age 11 years. Therefore, we recommend using the same treatments as in adults.

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on a massive amount of audio tracks from YouTube videos and encompassing over 500 classes of everyday sounds. However, AudioSet is not an open datasetits release consists of pre-computed audio features (instead of waveforms), which limits the adoption of some SER methods. Downloading the original audio tracks is also problematic due to constituent YouTube videos gradually disappearing and usage rights issues, which casts doubts over the suitability of this resource for systems' benchmarking. To provide an alternative benchmark dataset and thus foster SER research, we introduce FSD50K, an open dataset containing over 51k audio clips totalling over 100h of audio manually labeled using 200 classes drawn from the AudioSet Ontology. The audio clips are licensed under Creative Commons licenses, making the dataset freely distributable (including waveforms). We provide a detailed description of the FSD50K creation process, tailored to the particularities of Freesound data, including challenges encountered and solutions adopted. We include a comprehensive dataset characterization along with discussion of limitations and key factors to allow its audio-informed usage. Finally, we conduct sound event classification experiments to provide baseline systems as well as insight on the main factors to consider when splitting Freesound audio data for SER. Our goal is to develop a dataset to be widely adopted by the community as a new open benchmark for SER research.